RUS  ENG
Full version
JOURNALS // Journal of Samara State Technical University, Ser. Physical and Mathematical Sciences // Archive

Vestn. Samar. Gos. Tekhn. Univ., Ser. Fiz.-Mat. Nauki [J. Samara State Tech. Univ., Ser. Phys. Math. Sci.], 2012 Issue 1(26), Pages 183–191 (Mi vsgtu990)

This article is cited in 2 papers

Mathematical Modeling

Neural network training acceleration using NVIDIA CUDA technology for image recognition

A. A. Fertsev

Mordovian State University by N.~P.~Ogarev, Saransk

Abstract: In this paper, an implementation of neural network trained by algorithm based on Levenberg-Marquardt method is presented. Training of neural network increased by almost 9 times using NVIDIA CUDA technology. Implemented neural network is used for the recognition of noised images.

Keywords: Image recognition, neural networks, Levenberg-Marquardt method, graphics processing unit, CUDA.

UDC: 004.032.26

MSC: Primary 62M45; Secondary 94A08

Original article submitted 25/VIII/2011
revision submitted – 30/XI/2011

DOI: 10.14498/vsgtu990



Bibliographic databases:


© Steklov Math. Inst. of RAS, 2024